Share via

ManyModelsInferenceParameters Class

  • Reference

Parameters used for ManyModels inference pipeline.

Inheritance
azureml.train.automl.runtime._solution_accelorators.data_models.pipeline_parameters.InferencePipelineParameters
ManyModelsInferenceParameters

Constructor

ManyModelsInferenceParameters(partition_column_names: str, time_column_name: str | None = None, target_column_name: str | None = None, inference_type: str | None = None, forecast_mode: str = 'recursive', step: int = 1, forecast_quantiles: float | List[float] | None = None)

Parameters

Name Description
partition_column_names
Required
str

The names of columns used to group your models. For timeseries, the groups must not split up individual time-series. That is, each group must contain one or more whole time-series.
time_column_name
str

Time column name only if the inference dataset is a timeseries.

Default value: None
target_column_name
str

Target column name only if the inference dataset has the target column.

Default value: None
inference_type
str

Which inference method to use on the model. Possible values are 'forecast', 'predict_proba', and 'predict'.

Default value: None
forecast_mode
str

The type of forecast to be used, either 'rolling' or 'recursive', defaults to 'recursive'.

Default value: recursive
step
int

Number of periods to advance the forecasting window in each iteration (for rolling forecast only), defaults to 1.

Default value: 1
forecast_quantiles

Optional list of quantiles to get forecasts for.

Default value: None

Methods

validate

Validates the supplied parameters.

validate

Validates the supplied parameters.

validate()